As of October 22, 2026, DeepSeek V4 Pro 0813 ranks #38 of 123 models overall with 60.8 ±8.5 on the LLMBenchmark Index. DeepSeek V4 Pro 0813 ranks #37 of 108 in math, its strongest category. DeepSeek V4 Pro 0813 costs $0.66 per million input tokens and $1.98 per million output tokens. DeepSeek V4 Pro 0813 was released on August 12, 2026.
DeepSeek V4 Pro 0813's output price ranks 183 of 349 priced models, counting from the cheapest.
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
deepseek/deepseek-v4-pro-0813 The tick on a coding bar is the median of every model measured on it. Outside coding, the place is this model's rank on that board. A board that never ran the model says so.
Measured in 6 of 7 categories. A place counts only the models measured on that board.
The index averages only the coding benchmarks that have a result; the others are skipped, never filled in. How it is weighted
Not measured on Aider polyglot, SWE-bench Verified, SWE-bench Lite, SWE-bench (full test set), SWE-bench Multimodal, SWE-bench Multilingual, SWE-bench Multimodal (Vals AI), LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run), Terminal-Bench, DeepSWE, FrontierSWE, GSO-Bench, MirrorCode, Cybench, LMArena WebDev: from an image, SciCode
Not measured on Design Arena: agents building web apps, Design Arena: agents building full-stack apps, Design Arena: agents building mobile apps, Design Arena: agents building Android apps, Design Arena: agents building Godot games, Design Arena: agents building games, Design Arena: HTML slides, Design Arena: PowerPoint slides, Design Arena: spreadsheets, LiveBench research, LiveBench browser, LiveBench long agentic, BioMysteryBench (Vals AI), Vals Science Index, Time Horizon Index (Vals AI), CUA-bench (Vals AI), Robo-bench (Vals AI), τ²-Bench Telecom, METR time horizons, Remote Labor Index, GDPval, OSWorld 2.0, BALROG, DeepResearch Bench, PostTrainBench, TheAgentCompany, OSWorld, SpireClimb, Vending-Bench 2, LMArena Search, Berkeley Function Calling Leaderboard (BFCL), BrowseComp-Plus
Not measured on LiveBench reasoning, MysteryMechanism (Vals AI), MMMU Pro (Vals AI), Humanity's Last Exam, SimpleBench, EBR-bench, VPCT, BIG-Bench Hard, LMArena Vision: diagrams, LMArena Vision: homework, Kagi LLM Benchmark
Not measured on AIME, MATH 500 (Vals AI), MGSM (Vals AI), AA Math Index, AIME 2025 (Artificial Analysis run), MATH level 5, GSM8K
Not measured on CaseLaw (Vals AI), MortgageTax (Vals AI), MedQA (Vals AI), MMLU Pro (Artificial Analysis run), MMLU, GeoBench, AI2 Reasoning Challenge, FACTS Benchmark Suite
Not measured on Design Arena: websites, Design Arena: UI components, Design Arena: game dev, Design Arena: data viz, Design Arena: 3D, Design Arena: all code categories, Design Arena: SVG, Design Arena: ASCII art, LiveBench design
Not measured on LiveBench data analysis, Public Benefits Bench (Vals AI), SAGE (Vals AI), Vals Multimodal Index, IFBench, Fiction.LiveBench, Creative writing (Lech Mazur), CL-bench, Surface Evolver Bench, Furniture assembly, ExploitBench, HellaSwag, WinoGrande, PIQA, CL-bench Life, LMArena Vision, LMArena Text: German, LMArena Text: Japanese, LMArena Text: Polish, LMArena Vision: English, LMArena Vision: Chinese, LMArena Vision: reading text, LMArena Vision: humor, LMArena Vision: captioning, LMArena Vision: recognizing things, LMArena Vision: creative writing, LMArena Document
Not measured on Design Arena: images, Design Arena: graphic design, Design Arena: logos, LMArena Text to Image, LMArena Image Edit
Public boards shown as published (Vals AI, Artificial Analysis, Design Arena) and kept out of the coding index. Each links to its source on the benchmark page.
| Benchmark | Result | Index weight |
|---|---|---|
| Aider polyglotCoding | Not measured | Not in index |
| SWE-bench VerifiedCoding | Not measured | Not in index |
| SWE-bench LiteCoding | Not measured | Not in index |
| SWE-bench (full test set)Coding | Not measured | Not in index |
| SWE-bench MultimodalCoding | Not measured | Not in index |
| SWE-bench MultilingualCoding | Not measured | Not in index |
| LiveBench codingCoding | Not measured | 15% |
| LMArena WebDevCoding | 1582 | 10% |
| Vals IndexGeneral | 53.0% | Not in index |
| GPQA DiamondReasoning | 92.4% | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | 87.0% | Not in index |
| AA Intelligence IndexIntelligence | 36.0 | Not in index |
| AA Coding IndexCoding | 68.8 | Not in index |
| AA Agentic IndexAgentic work | 41.3 | Not in index |
| Design Arena: websitesWeb design | Not measured | Not in index |
| Design Arena: UI componentsWeb design | Not measured | Not in index |
| Design Arena: game devWeb design | Not measured | Not in index |
| Design Arena: data vizWeb design | Not measured | Not in index |
| Design Arena: 3DWeb design | Not measured | Not in index |
| Design Arena: all code categoriesWeb design | Not measured | Not in index |
| Design Arena: SVGWeb design | Not measured | Not in index |
| Design Arena: ASCII artWeb design | Not measured | Not in index |
| Design Arena: agents building web appsAgentic work | Not measured | Not in index |
| Design Arena: agents building full-stack appsAgentic work | Not measured | Not in index |
| Design Arena: agents building mobile appsAgentic work | Not measured | Not in index |
| Design Arena: agents building Android appsAgentic work | Not measured | Not in index |
| Design Arena: agents building Godot gamesAgentic work | Not measured | Not in index |
| Design Arena: agents building gamesAgentic work | Not measured | Not in index |
| Design Arena: HTML slidesAgentic work | Not measured | Not in index |
| Design Arena: PowerPoint slidesAgentic work | Not measured | Not in index |
| Design Arena: spreadsheetsAgentic work | Not measured | Not in index |
| Design Arena: imagesImage generation | Not measured | Not in index |
| Design Arena: graphic designImage generation | Not measured | Not in index |
| Design Arena: logosImage generation | Not measured | Not in index |
| LiveBench reasoningReasoning | Not measured | Not in index |
| LiveBench data analysisGeneral | Not measured | Not in index |
| LiveBench researchAgentic work | Not measured | Not in index |
| LiveBench browserAgentic work | Not measured | Not in index |
| LiveBench long agenticAgentic work | Not measured | Not in index |
| LiveBench designWeb design | Not measured | Not in index |
| LiveCodeBench (Vals AI)Coding | 87.5% | Not in index |
| SWE-bench Verified (Vals AI)Coding | 96.4% | 15% |
| Terminal-Bench 4 (Vals AI)Coding | 14.1% | 25% |
| Vibe Code Bench (Vals AI)Coding | 82.3% | 20% |
| Code migration (Vals AI)Coding | 41.5% | Not in index |
| ProgramBench (Vals AI)Coding | 0.0% | Not in index |
| SREBench (Vals AI)Agentic work | 1.9% | Not in index |
| IOI (Vals AI)Coding | 51.6% | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | 54.7% | Not in index |
| SWE-bench Multimodal (Vals AI)Coding | Not measured | Not in index |
| Vibe Code Bench 1-100 (Vals AI)Coding | 17.5% | Not in index |
| SkillsBench (Vals AI)Coding | 53.8% | Not in index |
| CyberBench (Vals AI)Coding | 72.9% | Not in index |
| Finance Agent (Vals AI)Agentic work | 50.4% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 26.8% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 40.9% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | 10.8% | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 52.8% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | Not measured | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | 4.3% | Not in index |
| Vals Science IndexAgentic work | Not measured | Not in index |
| Time Horizon Index (Vals AI)Agentic work | Not measured | Not in index |
| CUA-bench (Vals AI)Agentic work | Not measured | Not in index |
| Robo-bench (Vals AI)Agentic work | Not measured | Not in index |
| Public Benefits Bench (Vals AI)General | Not measured | Not in index |
| MysteryMechanism (Vals AI)Reasoning | Not measured | Not in index |
| MMMU Pro (Vals AI)Reasoning | Not measured | Not in index |
| MATH 500 (Vals AI)Math | Not measured | Not in index |
| MGSM (Vals AI)Math | Not measured | Not in index |
| SAGE (Vals AI)General | Not measured | Not in index |
| LegalBench (Vals AI)Knowledge | 82.4% | Not in index |
| CaseLaw (Vals AI)Knowledge | Not measured | Not in index |
| CorpFin (Vals AI)Knowledge | 65.4% | Not in index |
| TaxEval (Vals AI)Knowledge | 73.1% | Not in index |
| MortgageTax (Vals AI)Knowledge | Not measured | Not in index |
| MedQA (Vals AI)Knowledge | Not measured | Not in index |
| MedCode (Vals AI)Knowledge | 42.5% | Not in index |
| MedScribe (Vals AI)General | 80.2% | Not in index |
| Vals Multimodal IndexGeneral | Not measured | Not in index |
| AA Math IndexMath | Not measured | Not in index |
| GPQA Diamond (Artificial Analysis run)Reasoning | 92.8% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 41.0% | Not in index |
| MMLU Pro (Artificial Analysis run)Knowledge | Not measured | Not in index |
| LiveCodeBench (Artificial Analysis run)Coding | Not measured | Not in index |
| SciCodeCoding | 51.0% | Not in index |
| Terminal-Bench Hard (Artificial Analysis run)Coding | Not measured | Not in index |
| IFBenchGeneral | Not measured | Not in index |
| Long context reasoning (AA-LCR)General | 80.3% | Not in index |
| τ²-Bench TelecomAgentic work | Not measured | Not in index |
| AIME 2025 (Artificial Analysis run)Math | Not measured | Not in index |
| Terminal-BenchCoding | Not measured | Not in index |
| DeepSWECoding | Not measured | Not in index |
| FrontierCodeCoding | 28.5% | 15% |
| FrontierSWECoding | Not measured | Not in index |
| GSO-BenchCoding | Not measured | Not in index |
| WeirdMLCoding | 66.2% | Not in index |
| MirrorCodeCoding | Not measured | Not in index |
| APEX-AgentsAgentic work | 47.3% | Not in index |
| METR time horizonsAgentic work | Not measured | Not in index |
| Remote Labor IndexAgentic work | Not measured | Not in index |
| GDPvalAgentic work | Not measured | Not in index |
| OSWorld 2.0Agentic work | Not measured | Not in index |
| BALROGAgentic work | Not measured | Not in index |
| DeepResearch BenchAgentic work | Not measured | Not in index |
| PostTrainBenchAgentic work | Not measured | Not in index |
| GPQA Diamond (Epoch AI run)Reasoning | 91.7% | Not in index |
| ARC-AGIReasoning | 90.5% | Not in index |
| ARC-AGI-2Reasoning | 61.3% | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | Not measured | Not in index |
| Chess puzzlesReasoning | 46.0% | Not in index |
| Mystery game puzzlesReasoning | 43.0% | Not in index |
| EBR-benchReasoning | Not measured | Not in index |
| OTIS Mock AIMEMath | 98.6% | Not in index |
| FrontierMath, tiers 1 to 3Math | 64.6% | Not in index |
| FrontierMath, tier 4Math | 26.8% | Not in index |
| ProofBenchMath | 50.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 52.9% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 93.9% | Not in index |
| LMCAGeneral | 45.5% | Not in index |
| Fiction.LiveBenchGeneral | Not measured | Not in index |
| Creative writing (Lech Mazur)General | Not measured | Not in index |
| CL-benchGeneral | Not measured | Not in index |
| Surface Evolver BenchGeneral | Not measured | Not in index |
| Furniture assemblyGeneral | Not measured | Not in index |
| ExploitBenchGeneral | Not measured | Not in index |
| CybenchCoding | Not measured | Not in index |
| TheAgentCompanyAgentic work | Not measured | Not in index |
| OSWorldAgentic work | Not measured | Not in index |
| SpireClimbAgentic work | Not measured | Not in index |
| VPCTReasoning | Not measured | Not in index |
| BIG-Bench HardReasoning | Not measured | Not in index |
| AI2 Reasoning ChallengeKnowledge | Not measured | Not in index |
| HellaSwagGeneral | Not measured | Not in index |
| WinoGrandeGeneral | Not measured | Not in index |
| PIQAGeneral | Not measured | Not in index |
| CL-bench LifeGeneral | Not measured | Not in index |
| ALE-BenchCoding | 1403.2 | Not in index |
| Vending-Bench 2Agentic work | Not measured | Not in index |
| Epoch Capabilities IndexIntelligence | 155.6 | Not in index |
| LMArena TextGeneral | 1446 | Not in index |
| LMArena Text: codingCoding | 1469 | Not in index |
| LMArena Text: hard promptsReasoning | 1458 | Not in index |
| LMArena Text: mathMath | 1441 | Not in index |
| LMArena Text: instruction followingGeneral | 1448 | Not in index |
| LMArena Text: creative writingGeneral | 1439 | Not in index |
| LMArena VisionGeneral | Not measured | Not in index |
| LMArena Text: EnglishGeneral | 1457 | Not in index |
| LMArena Text: non-EnglishGeneral | 1431 | Not in index |
| LMArena Text: ChineseGeneral | 1481 | Not in index |
| LMArena Text: GermanGeneral | Not measured | Not in index |
| LMArena Text: JapaneseGeneral | Not measured | Not in index |
| LMArena Text: KoreanGeneral | 1449 | Not in index |
| LMArena Text: FrenchGeneral | 1446 | Not in index |
| LMArena Text: SpanishGeneral | 1435 | Not in index |
| LMArena Text: RussianGeneral | 1448 | Not in index |
| LMArena Text: PolishGeneral | Not measured | Not in index |
| LMArena Text: multi-turnGeneral | 1454 | Not in index |
| LMArena Text: longer queriesGeneral | 1458 | Not in index |
| LMArena Text: expertReasoning | 1459 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1463 | Not in index |
| LMArena Text: software and ITCoding | 1462 | Not in index |
| LMArena Text: mathematical workMath | 1443 | Not in index |
| LMArena Text: scienceKnowledge | 1457 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1446 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1459 | Not in index |
| LMArena Text: business and financeKnowledge | 1442 | Not in index |
| LMArena Text: writing and languageGeneral | 1443 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1424 | Not in index |
| LMArena WebDev: ReactCoding | 1588 | Not in index |
| LMArena WebDev: HTMLCoding | 1566 | Not in index |
| LMArena WebDev: from an imageCoding | Not measured | Not in index |
| LMArena Vision: EnglishGeneral | Not measured | Not in index |
| LMArena Vision: ChineseGeneral | Not measured | Not in index |
| LMArena Vision: reading textGeneral | Not measured | Not in index |
| LMArena Vision: diagramsReasoning | Not measured | Not in index |
| LMArena Vision: homeworkReasoning | Not measured | Not in index |
| LMArena Vision: humorGeneral | Not measured | Not in index |
| LMArena Vision: captioningGeneral | Not measured | Not in index |
| LMArena Vision: recognizing thingsGeneral | Not measured | Not in index |
| LMArena Vision: creative writingGeneral | Not measured | Not in index |
| LMArena SearchAgentic work | Not measured | Not in index |
| LMArena DocumentGeneral | Not measured | Not in index |
| LMArena Text to ImageImage generation | Not measured | Not in index |
| LMArena Image EditImage generation | Not measured | Not in index |
| Berkeley Function Calling Leaderboard (BFCL)Agentic work | Not measured | Not in index |
| Kagi LLM BenchmarkReasoning | Not measured | Not in index |
| BrowseComp-PlusAgentic work | Not measured | Not in index |
| SciCodeCoding | Not measured | Not in index |
| FACTS Benchmark SuiteKnowledge | Not measured | Not in index |
A list price says what a token costs. The cost per solved task says what a working answer costs, which is the number that decides.
Beside a result, many boards publish what the run cost, how long it took, the tokens it spent or the votes behind a rating. Each figure as its board printed it, one board per row.
| Board | Result | What the run cost | Also published |
|---|---|---|---|
| Vals Index | 53.0% | $2.50 per test | Duration, as printed 58m 03s |
| SWE-bench Verified (Vals AI) | 96.4% | $0.10 per test | Duration, as printed 4m 00s |
| Terminal-Bench 4 (Vals AI) | 14.1% | $3.31 per test | Duration, as printed 1h 32m |
| Vibe Code Bench (Vals AI) | 82.3% | $0.36 per test | Duration, as printed 1h 06m |
| Code migration (Vals AI) | 41.5% | $18.58 per test | Duration, as printed 3h 32m |
| ProgramBench (Vals AI) | 0.0% | $0.43 per test | Duration, as printed 1h 23m |
| SREBench (Vals AI) | 1.9% | $5.58 per test | Duration, as printed 2h 20m |
| IOI (Vals AI) | 51.6% | $2.15 per test | Duration, as printed 1h 07m |
| Terminal-Bench 2.1 (Vals AI) | 54.7% | $0.20 per test | Duration, as printed 14m 22s |
| Vibe Code Bench 1-100 (Vals AI) | 17.5% | $5.89 per test | Duration, as printed 37m 42s |
| SkillsBench (Vals AI) | 53.8% | $0.37 per test | Duration, as printed 11m 15s |
| CyberBench (Vals AI) | 72.9% | $0.59 per test | Duration, as printed 22m 33s |
| Finance Agent (Vals AI) | 50.4% | $0.88 per test | Duration, as printed 16m 15s |
|---|---|---|---|
| Tax Agent Bench (Vals AI) | 26.8% | $0.73 per test | Duration, as printed 26m 37s |
| Legal Research Bench (Vals AI) | 40.9% | $1.09 per test | Duration, as printed 42m 07s |
| Harvey's Legal Agent Benchmark (Vals AI) | 10.8% | $0.80 per test | Duration, as printed 10m 55s |
| Excel Modeling Benchmark (Vals AI) | 52.8% | $1.08 per test | Duration, as printed 37m 27s |
| Terminal-Bench-Science (Vals AI) | 4.3% | $4.63 per test | Duration, as printed 2h 16m |
| WeirdML | 66.2% | $0.191 per run | Median lines of code 318 |
| ProofBench | 50.0% | $0.0622 per test | Time per proof 12m 12s |
| ALE-Bench | 1403.2 | $0.0728 per problem | Tokens per problem 85,272 |
| LMArena WebDev | 1582 Elo | Not published | Votes 4,714 · Interval (±) ±9.5 |
| GPQA Diamond | 92.4% | Not published | Latency, as printed 4m 39s |
| MMLU Pro | 87.0% | Not published | Latency, as printed 60 s |
| LiveCodeBench (Vals AI) | 87.5% | Not published | Latency, as printed 4m 33s |
| LegalBench (Vals AI) | 82.4% | Not published | Latency, as printed 20 s |
| CorpFin (Vals AI) | 65.4% | Not published | Latency, as printed 33 s |
| TaxEval (Vals AI) | 73.1% | Not published | Latency, as printed 3m 46s |
| MedCode (Vals AI) | 42.5% | Not published | Latency, as printed 3m 01s |
| MedScribe (Vals AI) | 80.2% | Not published | Latency, as printed 2m 36s |
| APEX-Agents | 47.3% | Not published | Mean score 62.3% |
| LMArena Text | 1446 Elo | Not published | Votes 9,805 · Interval (±) ±6.6 |
| LMArena Text: coding | 1469 Elo | Not published | Votes 2,804 · Interval (±) ±11.3 |
| LMArena Text: hard prompts | 1458 Elo | Not published | Votes 6,526 · Interval (±) ±7.7 |
| LMArena Text: math | 1441 Elo | Not published | Votes 407 · Interval (±) ±27.8 |
| LMArena Text: instruction following | 1448 Elo | Not published | Votes 3,482 · Interval (±) ±10.3 |
| LMArena Text: creative writing | 1439 Elo | Not published | Votes 1,998 · Interval (±) ±13.8 |
| LMArena Text: English | 1457 Elo | Not published | Votes 3,765 · Interval (±) ±9.7 |
| LMArena Text: non-English | 1431 Elo | Not published | Votes 6,040 · Interval (±) ±7.9 |
| LMArena Text: Chinese | 1481 Elo | Not published | Votes 711 · Interval (±) ±22.3 |
| LMArena Text: Korean | 1449 Elo | Not published | Votes 197 · Interval (±) ±40.8 |
| LMArena Text: French | 1446 Elo | Not published | Votes 315 · Interval (±) ±33.1 |
| LMArena Text: Spanish | 1435 Elo | Not published | Votes 299 · Interval (±) ±32.3 |
| LMArena Text: Russian | 1448 Elo | Not published | Votes 1,233 · Interval (±) ±16.6 |
| LMArena Text: multi-turn | 1454 Elo | Not published | Votes 1,569 · Interval (±) ±15.3 |
| LMArena Text: longer queries | 1458 Elo | Not published | Votes 4,568 · Interval (±) ±9.2 |
| LMArena Text: expert | 1459 Elo | Not published | Votes 1,028 · Interval (±) ±18.4 |
| LMArena Text: hard prompts in English | 1463 Elo | Not published | Votes 2,490 · Interval (±) ±12.0 |
| LMArena Text: software and IT | 1462 Elo | Not published | Votes 4,090 · Interval (±) ±9.4 |
| LMArena Text: mathematical work | 1443 Elo | Not published | Votes 513 · Interval (±) ±26.1 |
| LMArena Text: science | 1457 Elo | Not published | Votes 1,527 · Interval (±) ±15.1 |
| LMArena Text: medicine and healthcare | 1446 Elo | Not published | Votes 623 · Interval (±) ±23.1 |
| LMArena Text: legal and government | 1459 Elo | Not published | Votes 825 · Interval (±) ±20.3 |
| LMArena Text: business and finance | 1442 Elo | Not published | Votes 1,804 · Interval (±) ±13.9 |
| LMArena Text: writing and language | 1443 Elo | Not published | Votes 2,636 · Interval (±) ±11.9 |
| LMArena Text: entertainment and media | 1424 Elo | Not published | Votes 2,463 · Interval (±) ±12.4 |
| LMArena WebDev: React | 1588 Elo | Not published | Votes 3,099 · Interval (±) ±11.7 |
| LMArena WebDev: HTML | 1566 Elo | Not published | Votes 548 · Interval (±) ±27.0 |